Autonomous AI agents that perform tasks independently
broxhq
Run manual test cases with an AI agent in a real browser
ryder_soc
OpenClaw channel plugin for the generic HTTP protocol
vibefixing
Reproducible adversarial eval for AI agents. Deterministic scoring, no model judge. Vibefixing publishes the eval; we don't compete on the leaderboard.
...moreLITS: LLM Inference via Tree Search — modular agentic reasoning framework.
MemHQ <[email protected]>
MemHQ adapter for LlamaIndex — chat memory and retriever backed by MemHQ.
Wuying AI Team
Python SDK for interacting with the Wuying AgentBay cloud runtime environment
Deterministic governance middleware for LangChain agents — policy enforcement, cost limits, tool allowlisting, NHI scope controls, and SARIF audit evidence. No LLM in the governance path.
...moreEpistemic Guardrails for LLM agents. Mitigates B2B risk via cryptographic verification.
AI agent memory system — sub-millisecond hybrid search (FAISS + FTS5 + RRF), knowledge graph, temporal awareness, LLM-powered extraction, entity resolution, conversation memory. Zero infrastructure. OpenAI/Anthropic/Ollama support.
...moreTiago Perez
CLI orchestrator for multi-step AI execution plans (Codex, Claude, Gemini, Copilot, Qwen, Ollama, Llama)
Post-inference command execution. LLM produces a phrase, never a shell command.
coderchatwang
CoderChat is an alternative to tools such as Void, Cursor, Qoder, Trae, and CodeBuddy.The core goal of this project is to benchmark the most user-friendly agent technology, reject token premium, and experience the charm of AI programming with the lowest token cost.
...moreAssassinticketcollector3649
Automate penetration testing tasks with an LLM-driven multi-agent framework designed for security assessment.
scotti1i
TikTok Shop GMV Max diagnostic framework - 4 steps + Layer ABCD (bilingual EN/中文)
LaobaiAi
CAIAO — Server-as-atomic-unit framework for tool orchestration. Turn every solver, tool, or external capability into an independent Server process.
...moregabrielvuksani
WIP: Currently finishing up Wotann before picking up Wotann Code again - The All-Father of AI agent harnesses. One install. Every model. Every channel. Full autonomy.
...moreaandbcct
一个轻量级开源AI个人助手框架，用于学习与实践个人agent助手架构设计，基于ReAct架构，由中间路由层连接客户端与底层组件，实现了多模型适配、多平台适配和会话管理。 每阶段的开发路线、开发日志、代码审查记录都在文档中，方便学习与了解整个框架从0开始的搭建过程。
...moreTuesdaythe13th
L4BYR1NTH: ARTIFEX Safety Evals
ai-driven-dev
Marketplace Framework AI-Driven Dev : Context Engineering, Plugins, Agents, Skills, Hooks, Templates, SDLC
whitejoce
A Linux terminal Agent powered by LLMs. Analyzes user input, decides whether to execute terminal commands, and always returns results in structured JSON.
...moreEpisodeYu
生产级 3GPP 5G 规范 RAG Agent：自然语言提问，回答带段落级原文引用 + 严格 grounding，覆盖 Rel-18/19 全部 TS。
zuowen7
Open-source Claude Code for academic papers — translate, write, review, and export research papers locally
Hereon-InstituteMS
OASiS — an open-source multi-physics and multi-code framework for verified computer simulations. Model Context Protocol (MCP) server connecting AI coding agents to 8 finite element solvers (FEniCSx, deal.II, 4C, NGSolve, scikit-fem, Kratos, DUNE-fem, FEBio) with cross-backend collation knowledge.
...moreDylPorter
Chat with Claude Code from your phone via Telegram. Uses your Max plan auth (no API key) — runs as a systemd service on your own machine.
...more